DeepEMD : few-shot image classification with differentiable Earth Mover’s Distance and structured classifiers

• Main Authors: Zhang, Chi, Cai, Yujun, Lin, Guosheng, Shen, Chunhua
• Other Authors: School of Computer Science and Engineering
• Format: Conference or Workshop Item
• Language: English
• Published: 2020
• Subjects: Engineering::Computer science and engineering; Deep Neural Networks; Earth Mover’s Distance (EMD)
• Online Access: https://hdl.handle.net/10356/144270
• Institution: Nanyang Technological University

In this paper, we address the few-shot classification task from a new perspective of optimal matching between image regions. We adopt the Earth Mover’s Distance (EMD) as a metric to compute a structural distance between dense image representations to determine image relevance. The EMD generates the...